Skip to content

KKenny0/card-skill / plugins/card-skill/skills/card-skill

card-skill

Unverified

Turn supplied text or evidence into PNG cards, article covers, and explanatory illustrations. Use for content-to-image requests, including card series and reading-note visuals.

FileKindSize
LICENSEother1.0 KB
README.mdmarkdown18.7 KB
README.zh-CN.mdmarkdown18.2 KB
SKILL.mdskill md13.7 KB
VERSIONother7 B
assets/big_template.htmlother2.0 KB
assets/capture4k.jsscript5.7 KB
assets/comic_template.htmlother1.8 KB
assets/cover-series/paper-wilderness/README.mdmarkdown1.5 KB
assets/cover-series/paper-wilderness/cooperation.pngbinary2.1 MB
assets/cover-series/paper-wilderness/layout.cssother523 B
assets/cover-series/paper-wilderness/master.pngbinary1.7 MB
assets/cover-series/paper-wilderness/rest.pngbinary2.3 MB
assets/cover-series/paper-wilderness/uncertainty.pngbinary2.0 MB
assets/fonts/DM-Sans-OFL.txtmarkdown4.3 KB
assets/fonts/DM-Serif-Display-OFL.txtmarkdown4.4 KB
assets/fonts/DMSans-Variable.ttfbinary234.5 KB
assets/fonts/DMSerifDisplay-Regular.ttfbinary74.8 KB
assets/fonts/FONT_SOURCES.mdmarkdown1.3 KB
assets/fonts/JetBrains-Mono-OFL.txtmarkdown4.3 KB
assets/fonts/JetBrainsMono-Variable.ttfbinary293.1 KB
assets/fonts/LICENSE-fonts.mdmarkdown1.7 KB
assets/fonts/NanxiChuxiasong.ttfbinary3.1 MB
assets/fonts/OFL-1.1.txtmarkdown4.0 KB
assets/fonts/XiangcuiDengcusong.ttfbinary22.3 MB
assets/fonts/local-fonts.cssother641 B
assets/fonts/香萃打字机体 W15.ttfbinary15.7 MB
assets/fonts/香萃打字机体 W40.ttfbinary15.5 MB
assets/gallery/article-boundary-legacy.pngbinary129.8 KB
assets/gallery/article-formula.pngbinary181.2 KB
assets/gallery/article-personal.pngbinary120.8 KB
assets/gallery/big.pngbinary157.0 KB
assets/gallery/comic.pngbinary3.4 MB
assets/gallery/editorial-wechat-cover.pngbinary760.3 KB
assets/gallery/infograph.pngbinary604.6 KB
assets/gallery/long.pngbinary960.7 KB
assets/gallery/manifest.jsonconfig6.2 KB
assets/gallery/poster.pngbinary335.6 KB
assets/gallery/reading-notes.pngbinary363.9 KB
assets/gallery/reading-report.pngbinary366.9 KB
assets/gallery/sketchnote.pngbinary603.9 KB
assets/gallery/whiteboard.pngbinary583.2 KB
assets/infograph-comparison-notes.cssother951 B
assets/infograph_template.htmlother2.6 KB
assets/logo.pngbinary1.0 MB
assets/long_template.htmlother3.1 KB
assets/open-source-tool/tool-cli-1.pngbinary419.5 KB
assets/open-source-tool/tool-cli-2.pngbinary427.9 KB
assets/open-source-tool/tool-cli-3.pngbinary467.6 KB
assets/open-source-tool/tool-launch-1.pngbinary483.1 KB
assets/open-source-tool/tool-launch-2.pngbinary408.5 KB
assets/open-source-tool/tool-launch-3.pngbinary547.6 KB
assets/open-source-tool/tool-launch-4.pngbinary449.0 KB
assets/poster_template.htmlother18.5 KB
assets/readme-showcase.pngbinary773.4 KB
assets/sketchnote-wandering-notes.cssother1.7 KB
assets/sketchnote_template.htmlother16.9 KB
assets/whiteboard-notes.cssother2.2 KB
docs/astra-migration.mdmarkdown4.4 KB
docs/current-architecture.mdmarkdown7.8 KB
evals/agent-cases.jsonconfig34.0 KB
evals/cardbench-results.jsonconfig19.5 KB
evals/check-assertions.mjsscript25.8 KB
evals/check-job-assertions.mjsscript25.3 KB
evals/cover-art-agent-cases.jsonconfig4.5 KB
evals/evals.jsonconfig51.3 KB
evals/fixtures/article-diagram-personal.jsonconfig11.4 KB
evals/fixtures/big-reading.jsonconfig3.7 KB
evals/fixtures/comic-moment-notes/interaction.pngbinary2.2 MB
evals/fixtures/comic-moment-notes/jobs.mjsscript2.9 KB
evals/fixtures/comic-moment-notes/rousseau.pngbinary2.1 MB
evals/fixtures/comic-moment-notes/uncertainty-art.pngbinary1.6 MB
evals/fixtures/font-load-failed.htmlother830 B
evals/fixtures/infograph-comparison-notes/a2a.jsonconfig5.3 KB
evals/fixtures/infograph-comparison-notes/cursor.jsonconfig4.4 KB
evals/fixtures/infograph-comparison-notes/dense.jsonconfig7.1 KB
evals/fixtures/infograph-comparison-notes/interaction.jsonconfig6.3 KB
evals/fixtures/infograph-comparison-notes/loading.jsonconfig5.4 KB
evals/fixtures/infograph-comparison-notes/metrics.jsonconfig4.4 KB
evals/fixtures/infograph-comparison-notes/overview.jsonconfig6.9 KB
evals/fixtures/infograph-comparison-notes/stability.jsonconfig4.6 KB
evals/fixtures/long-notes.jsonconfig9.5 KB
evals/fixtures/poster-field-notes.jsonconfig2.2 KB
evals/fixtures/retired-cover-pair.jsonconfig7.5 KB
evals/fixtures/sketchnote-wandering-notes/a2a.jsonconfig6.3 KB
evals/fixtures/sketchnote-wandering-notes/rousseau.jsonconfig5.1 KB
evals/fixtures/sketchnote-wandering-notes/uncertainty.jsonconfig5.1 KB
evals/fixtures/svg-text-outside-viewbox.htmlother1.3 KB
evals/fixtures/svg-text-overflow.htmlother1.0 KB
evals/fixtures/whiteboard-notes-series.job.jsonconfig10.3 KB
evals/fixtures/whiteboard-notes.jsonconfig15.2 KB
evals/fresh-context-long-results.jsonconfig1.3 KB
evals/fresh-context-results.jsonconfig10.6 KB
evals/gallery/creative/comic.jsonconfig2.4 KB
evals/gallery/creative/infograph.jsonconfig4.4 KB
evals/gallery/creative/sketchnote.jsonconfig5.1 KB
evals/gallery/jobs/article-boundary-legacy.jsonconfig1.7 KB
evals/gallery/jobs/article-formula.jsonconfig2.0 KB
evals/gallery/jobs/article-personal.jsonconfig1.8 KB
evals/gallery/jobs/big.jsonconfig1.2 KB
evals/gallery/jobs/editorial-wechat-cover.jsonconfig2.1 KB
evals/gallery/jobs/long.jsonconfig5.1 KB
evals/gallery/jobs/poster.jsonconfig1.1 KB
evals/gallery/jobs/reading-notes.jsonconfig1.7 KB
evals/gallery/jobs/reading-report.jsonconfig1.2 KB
evals/gallery/jobs/whiteboard.jsonconfig3.0 KB
evals/run-discovery.mjsscript10.1 KB
evals/run-fresh-context.mjsscript26.1 KB
evals/runtime-policy.mjsscript1.3 KB
package-lock.jsonmanifest1.7 KB
package.jsonmanifest1.0 KB
references/article-diagram-personal.mdmarkdown5.6 KB
references/codex-inline-preview.mdmarkdown8.4 KB
references/cover-paper-wilderness.mdmarkdown5.9 KB
references/design-index.mdmarkdown3.7 KB
references/design-memory.jsonconfig154 B
references/eval-protocol.mdmarkdown11.2 KB
references/mode-article-diagram.mdmarkdown594 B
references/mode-big.mdmarkdown3.6 KB
references/mode-comic.mdmarkdown4.3 KB
references/mode-editorial-image.mdmarkdown3.0 KB
references/mode-infograph.mdmarkdown5.3 KB
references/mode-long.mdmarkdown4.2 KB
references/mode-poster.mdmarkdown12.3 KB
references/mode-sketchnote.mdmarkdown2.0 KB
references/mode-whiteboard.mdmarkdown1.8 KB
references/personal-style-migration.mdmarkdown2.8 KB
references/poster-field-notes.mdmarkdown3.3 KB
references/runtime.mdmarkdown2.9 KB
references/sketchnote-wandering-notes.mdmarkdown5.6 KB
references/source-material.mdmarkdown4.0 KB
references/source-open-source-tool.mdmarkdown5.1 KB
references/source-weread.mdmarkdown8.0 KB
references/taste.mdmarkdown15.0 KB
references/visual-job.mdmarkdown10.7 KB
references/visual-review.mdmarkdown4.7 KB
references/visual-taxonomy.mdmarkdown2.1 KB
references/whiteboard-reasoning-notes.mdmarkdown4.9 KB
schemas/article-diagram.jsonconfig5.1 KB
schemas/big.jsonconfig3.8 KB
schemas/comic.jsonconfig2.0 KB
schemas/editorial-image.jsonconfig8.5 KB
schemas/infograph.jsonconfig1.5 KB
schemas/long.jsonconfig6.5 KB
schemas/poster.jsonconfig13.8 KB
schemas/sketchnote.jsonconfig1.4 KB
schemas/visual-job.jsonconfig11.4 KB
schemas/visual-review.jsonconfig2.5 KB
schemas/whiteboard.jsonconfig8.5 KB
scripts/batch_render_covers.jsscript15.0 KB
scripts/batch_render_covers_dark.jsscript11.6 KB
scripts/card.jsscript22.4 KB
scripts/check-output.mjsscript57.4 KB
scripts/check-update.mjsscript32.7 KB
scripts/gallery-jobs.mjsscript12.5 KB
scripts/hash-reviewed-candidate.mjsscript799 B
scripts/lib/big-reading.jsscript3.0 KB
scripts/lib/candidate-snapshot.jsscript3.9 KB
scripts/lib/comic-art.jsscript958 B
scripts/lib/designs.jsscript9.3 KB
scripts/lib/escape.jsscript919 B
scripts/lib/file-access.jsscript10.6 KB
scripts/lib/long-notes.jsscript1.6 KB
scripts/lib/mode-selector.jsscript1.7 KB
scripts/lib/output-checks.jsscript26.0 KB
scripts/lib/personal-diagram.jsscript4.2 KB
scripts/lib/publish-artifacts.jsscript4.0 KB
scripts/lib/schema.jsscript31.5 KB
scripts/lib/test-kit.jsscript3.1 KB
scripts/lib/update-launcher.jsscript1.9 KB
scripts/lib/update-state.jsscript4.8 KB
scripts/lib/visual-job.jsscript39.5 KB
scripts/lib/visual-review.jsscript5.8 KB
scripts/lib/whiteboard-notes.jsscript5.8 KB
scripts/package-skill.mjsscript1.4 KB
scripts/publish-reviewed-job.mjsscript25.4 KB
scripts/render-job.mjsscript15.4 KB
scripts/renderers/article-diagram-personal.jsscript10.4 KB
scripts/renderers/article-diagram.jsscript133 B
scripts/renderers/big.jsscript5.6 KB
scripts/renderers/editorial-image.jsscript9.4 KB
scripts/renderers/long.jsscript5.9 KB
scripts/renderers/poster.jsscript12.3 KB
scripts/renderers/studio-composition.jsscript6.7 KB
scripts/renderers/whiteboard-notes.jsscript3.0 KB
scripts/renderers/whiteboard.jsscript104 B
scripts/setup-runtime.mjsscript2.7 KB
scripts/smoke.mjsscript8.5 KB
scripts/validate-big-reading.mjsscript3.5 KB
scripts/validate-comic-notes.mjsscript7.1 KB
scripts/validate-editorial-cover.mjsscript14.0 KB
scripts/validate-infograph-notes.mjsscript5.1 KB
scripts/validate-long-notes.mjsscript3.4 KB
scripts/validate-personal-defaults.mjsscript3.1 KB
scripts/validate-personal-diagram.mjsscript5.7 KB
scripts/validate-sketchnote-notes.mjsscript5.4 KB
scripts/validate-visual-job.mjsscript89.5 KB
scripts/validate-whiteboard-notes.mjsscript4.9 KB
scripts/validate.mjsscript100.2 KB

evals/agent-cases.json

View on GitHub
{
  "schema_version": 2,
  "protocol": "references/eval-protocol.md",
  "cases": [
    {
      "id": "wechat-cover",
      "request": "把摘要做成纸上荒野公众号头图。使用当前技能目录内 assets/cover-series/paper-wilderness/cooperation.png 作为用户指定插画,先解析成绝对本地路径,不重新生图。使用 wechat-cover 比例。只输出 Visual Job v3 JSON。",
      "source_text": "采购助手把资质与风险评估交给外部机构的 Agent;双方交换任务和结果,内部实现保持不可见。",
      "publish_target": "wechat-cover",
      "tier": "stable",
      "modes": [
        "editorial-image"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "use",
        "aspect",
        "cover_art",
        "cover_series"
      ],
      "required_terms": [
        "内部",
        "不可见"
      ],
      "required_contract_patterns": [
        "协作|交换[^。!?]{0,20}结果"
      ]
    },
    {
      "id": "blog-hero",
      "request": "Create a Paper Wilderness blog header using the verified wechat-cover aspect. Use the supplied illustration assets/cover-series/paper-wilderness/rest.png inside the current skill directory; resolve its absolute local path. Do not generate new artwork. Output only Visual Job v3 JSON.",
      "source_text": "Rest can mean staying with the present instead of escaping into the past or future.",
      "publish_target": "blog-hero",
      "tier": "stable",
      "modes": [
        "editorial-image"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "use",
        "aspect",
        "cover_art",
        "cover_series"
      ],
      "required_terms": [
        "Rest"
      ]
    },
    {
      "id": "article-split",
      "request": "为下面两个独立章节分别做正文解释图,不要把全文塞进一张图。只输出 Visual Job JSON。",
      "source_text": "第一节:输入契约决定系统允许什么。第二节:发布回执证明系统实际做了什么。",
      "publish_target": "article-body",
      "tier": "stable",
      "modes": [
        "article-diagram"
      ],
      "outputs": [
        2,
        2
      ],
      "source_units": [
        2,
        2
      ],
      "source_unit_assignment": "one-to-one",
      "required_contract_fields": [
        "title"
      ],
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "输入",
            "契约"
          ],
          "contract_terms": [
            "输入",
            "契约"
          ]
        },
        {
          "source_terms": [
            "发布",
            "回执"
          ],
          "contract_terms": [
            "发布",
            "回执"
          ]
        }
      ],
      "exclusive_source_contract_mappings": true
    },
    {
      "id": "article-personal-default",
      "request": "把下面这段内容做成一张正文解释图。只输出 Visual Job JSON。",
      "source_text": "项目经历三个阶段:一月确定研究问题,二月完成小规模试验,三月整理结果。这是三个阶段的先后顺序,不表示各阶段耗时相同。",
      "publish_target": "article-body",
      "tier": "stable",
      "modes": [
        "article-diagram"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "personal_layout",
        "render_plan",
        "formula",
        "sentence",
        "structure"
      ],
      "required_terms": [
        "一月",
        "二月",
        "三月",
        "不"
      ]
    },
    {
      "id": "social-big",
      "request": "把这句话做成一张单图社媒观点卡。只输出 Visual Job JSON。",
      "source_text": "能重建,才算能验证。",
      "publish_target": "social-single",
      "tier": "stable",
      "modes": [
        "big"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "phrase"
      ],
      "required_terms": [
        "重建",
        "验证"
      ]
    },
    {
      "id": "poster",
      "request": "把下面三点做成一个纯排版社媒系列卡组,每点一张。Visual Job 使用三个 outputs,每个 poster contract 只含一张 card;每个 artifact 的 visual_plan.visual_metaphor 必须为 null,不承诺链条、轨道、缩略图或其他 poster renderer 无法呈现的图形。每个 contract 顶层的 title 必须是非空简短步骤名,且不要逐字重复正文;cards[].title 可作为独立的短主题标签。每张卡逐字保留对应步骤的标题句,并用同一 source unit 内的说明句形成正文。只输出 Visual Job JSON。",
      "source_text": "一、先确认来源。记录出处、作者与上下文,让后续判断建立在可追溯的信息上。二、再选择视觉结构。根据内容关系选择层级、流程或比较结构,让形式服务于核心信息。三、最后检查真实 PNG。同时查看缩略图与全尺寸成品,确认层级、负载和风格都达到发布标准。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        3,
        3
      ],
      "source_units": [
        3,
        3
      ],
      "source_unit_assignment": "one-to-one",
      "required_contract_fields": [
        "cards"
      ],
      "required_card_term_groups": [
        [
          "来源"
        ],
        [
          "视觉结构"
        ],
        [
          "PNG"
        ]
      ],
      "exclusive_card_term_groups": true,
      "artifact_outputs": [
        3,
        3
      ]
    },
    {
      "id": "long",
      "request": "把下面短文做成一张长阅读卡,不要拆成系列。只输出 Visual Job JSON。",
      "source_text": "工具的价值不在于替人完成一次动作,而在于把判断、执行和证据连成一条可复用的路径。判断让人知道为什么做,执行让结果发生,证据让后来者可以复核。",
      "publish_target": "long-read",
      "tier": "stable",
      "modes": [
        "long"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "body"
      ],
      "required_terms": [
        "判断",
        "执行",
        "证据"
      ]
    },
    {
      "id": "whiteboard",
      "request": "把下面决策关系做成一张 whiteboard 推演图。render_contract 使用四个纵向 chain steps,每条依次是 highlight 节点、带方向箭头的 muted 关系、highlight 节点:①事实 →约束→ 选择;②选择 →决定→ 动作;③动作 →产生→ 回执;④回执 ↺更新→ 事实。不要合并成单个横排网格。只输出 Visual Job JSON。",
      "source_text": "事实先约束选择,选择决定动作,动作产生回执,回执再更新事实。",
      "publish_target": "whiteboard",
      "tier": "stable",
      "modes": [
        "whiteboard"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "steps"
      ],
      "required_terms": [
        "事实",
        "选择",
        "动作",
        "回执"
      ]
    },
    {
      "id": "reading-notes",
      "request": "把下面两条明确指定的个人划线做成 reading-notes 卡组,每条一张,不要补书中不存在的内容。Visual Job 必须只有一个 output,使用 poster 的 field-notes variant,contract 内恰好两张 cards;顶层 title 用书名,cards[].title 只写不重复原句的简短主题标签,每条原文只放在对应 reading_unit.quote。只输出 Visual Job JSON。",
      "source_text": "《示例书》划线一:边界让自由变得可持续。划线二:记录不是回顾,而是下一次行动的入口。",
      "publish_target": "reading-notes",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "variant",
        "cards"
      ],
      "artifact_outputs": [
        2,
        2
      ],
      "required_card_term_groups": [
        [
          "边界",
          "自由"
        ],
        [
          "记录",
          "行动"
        ]
      ],
      "exclusive_card_term_groups": true,
      "forbidden_terms": [
        "作者认为",
        "全书"
      ]
    },
    {
      "id": "studio-editorial-body",
      "request": "为下面段落做一张正文概念隐喻图,不要做标题模板。只输出 Visual Job JSON。",
      "source_text": "注意力像一束窄光:中心信息被照亮时,外围材料仍然存在,只是暂时退到暗处。",
      "publish_target": "article-body",
      "tier": "studio",
      "modes": [
        "editorial-image"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "use",
        "aspect",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "注意力"
      ]
    },
    {
      "id": "comparison-infograph",
      "request": "把本地处理与云端处理的差异做成一张左右比较信息图。左列固定呈现“本地处理 / 数据不离开设备 / 协作成本较高”,右列固定呈现“云端处理 / 数据交给远端服务 / 协作方便”;只用一条“数据去向”方向关系,不添加底部第三套总结轴或改写语序。content_html 使用 header 与 .compare;.compare 固定为三列网格 minmax(0,1fr) 160px minmax(0,1fr)、高 520px、align-items:center、gap 20px、水平 padding 40px;左右 .side 固定 min-width:0、min-height:340px,使用 flex 垂直居中、gap 24px、padding 28px,不使用 space-between;中间 .axis 宽 160px、字号至少 32px,并以明显箭头连接两列。列标题不超过 52px,主句固定 40px、允许自然换成最多两行,禁止 nowrap 和 transform;取舍 36px。只输出 Visual Job JSON。",
      "source_text": "本地处理:数据不离开设备,协作成本较高。云端处理:协作方便,但需要把数据交给远端服务。",
      "publish_target": "social-single",
      "tier": "studio",
      "modes": [
        "infograph"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "本地",
        "云端",
        "数据"
      ]
    },
    {
      "id": "data-infograph",
      "request": "把下面真实数据做成单张信息图,不补充数据。只输出 Visual Job JSON。",
      "source_text": "本周完成 12 次运行,其中 9 次一次通过,3 次经过修订后通过。",
      "publish_target": "social-single",
      "tier": "studio",
      "modes": [
        "infograph"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "12",
        "9",
        "3"
      ]
    },
    {
      "id": "conflict-comic",
      "request": "把下面有冲突和转折的短故事做成一页三格漫画,使用短标题“完成?”。三格依次使用固定短标题:①“以为完成”;②“发布前|无法重建”;③“补上回执|每一步都有证据”。沿用模板标题区,不覆盖 .card/.panels 尺寸;每格内部使用左右分区,视觉对象最多占 35%,文字区至少占 65%,文本不使用 absolute 定位,图形不得进入文字区;不使用巨型“停/断”等 SFX、手写 br 或超出 panel 的装饰。只输出 Visual Job JSON。",
      "source_text": "团队以为任务已经完成,直到发布前才发现没有任何人能重建结果。他们回到起点补上回执,这次每一步都有证据。",
      "publish_target": "social-single",
      "tier": "studio",
      "modes": [
        "comic"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "重建",
        "回执",
        "证据"
      ]
    },
    {
      "id": "reflective-sketchnote",
      "request": "把下面从失败到顿悟的个人反思做成一张精简 sketchnote,只用三个主站点:①一次写完→卡住;②留下可检查的草稿;③写作开始向前。标题用“先留下”,除来源短句外不要扩写方法论。这个案例使用三阶段递进布局而非视觉隐喻,artifact 的 visual_plan.visual_metaphor 必须为 null,不承诺弧线、路径或其他必须另外兑现的图形。content_html 只使用顶部标题和一个 .arc,.arc 内正好三个 .station,不添加结语或重复总结;custom_css 固定 .page 高 1500px,顶部标题区约 300px,.arc 高 1120px、padding:40px 64px 64px、三行等分网格、gap 24px;每个 .station 使用 380px minmax(0,1fr) 两列、align-items:center、gap 32px、padding 28px 36px,让站点标题与正文横向配对并填满卡片;站点 h2 固定 40px 且 white-space:nowrap,三个固定短标题都必须保持单行。禁止 drop-cap、::first-letter 放大、手写 br、正文 nowrap、负定位和超过 8px 的阴影;正文使用正常 36px、行高 1.45、常规字重。只输出 Visual Job JSON。",
      "source_text": "我总想一次写完,结果每次都卡住。后来我只要求自己先留下一个可检查的草稿,写作终于开始向前。",
      "publish_target": "social-single",
      "tier": "studio",
      "modes": [
        "sketchnote"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "草稿",
        "检查",
        "向前"
      ]
    },
    {
      "id": "timeline-infograph",
      "request": "把下面三个时间节点做成一张时间线信息图。只输出 Visual Job JSON。",
      "source_text": "周一确认来源,周三完成首版,周五根据真实图片复查并发布。",
      "publish_target": "social-single",
      "tier": "studio",
      "modes": [
        "infograph"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "周一",
        "周三",
        "周五"
      ]
    },
    {
      "id": "mixed-claim-mechanism",
      "request": "把一句主张和一个独立机制分别做成两张图。主张用 big;机制用 article-diagram 个人关系布局,完整保留输入契约、允许动作、执行、回执与更新下一次输入的关系。只输出 Visual Job JSON。",
      "source_text": "主张:没有回执,就没有完成。机制:输入契约限制允许动作,执行结果生成回执,回执再更新下一次输入。",
      "publish_target": "social-single",
      "tier": "stable",
      "modes": [
        "mixed"
      ],
      "outputs": [
        2,
        2
      ],
      "source_units": [
        2,
        2
      ],
      "source_unit_assignment": "one-to-one",
      "required_contract_fields": [],
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "没有回执",
            "没有完成"
          ],
          "contract_terms": [
            "回执",
            "完成"
          ]
        },
        {
          "source_terms": [
            "输入契约",
            "允许动作"
          ],
          "contract_terms": [
            "契约",
            "输入"
          ]
        }
      ],
      "exclusive_source_contract_mappings": true
    },
    {
      "id": "user-whiteboard-override",
      "request": "我明确要 whiteboard,不要自动换 mode:把这句话展开成一条最短推理链。只输出 Visual Job JSON。",
      "source_text": "约束让选择变少,也让行动变得可验证。",
      "publish_target": "social-single",
      "tier": "stable",
      "modes": [
        "whiteboard"
      ],
      "selection_source": "user-override",
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "steps"
      ],
      "required_terms": [
        "约束",
        "选择",
        "验证"
      ]
    },
    {
      "id": "open-source-cli-adaptive",
      "visual_job_version": 3,
      "request": "用 evidence-first 路由介绍这个开源 CLI。不要指定固定模板;只生成证据足以支持的卡片。必须使用一个 poster output 和三张 cards,artifact roles 依次为 problem、command、output。命令逐字保留,历史素材只进入 rejected evidence,不得出现在 cards 或 artifact 引用中。只输出 Visual Job JSON。",
      "source_text": "项目类型:CLI。当前官方 README 说明输入是一个代码仓库。Quick start 命令:npx repo-packer@latest。当前输出是一个可供 AI 检查的文本包。历史素材:旧项目名 repopack 的输出截图,已经过期,不得作为当前证据。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "source_units": [
        4,
        5
      ],
      "artifact_outputs": [
        3,
        3
      ],
      "required_artifact_roles": [
        "problem",
        "command",
        "output"
      ],
      "required_contract_fields": [
        "cards"
      ],
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "代码仓库"
          ],
          "contract_terms": [
            "代码仓库"
          ]
        },
        {
          "source_terms": [
            "npx",
            "repo-packer"
          ],
          "contract_terms": [
            "npx repo-packer@latest"
          ]
        },
        {
          "source_terms": [
            "文本包"
          ],
          "contract_terms": [
            "文本包"
          ]
        }
      ],
      "exclusive_source_contract_mappings": true,
      "required_card_term_groups": [
        [
          "代码仓库"
        ],
        [
          "npx repo-packer@latest"
        ],
        [
          "文本包"
        ]
      ],
      "exclusive_card_term_groups": true,
      "rejected_source_expectations": [
        {
          "source_terms": [
            "repopack",
            "过期"
          ],
          "strength": "unusable",
          "freshness": "stale"
        }
      ],
      "forbidden_terms": [
        "repopack"
      ]
    },
    {
      "id": "open-source-launch-adaptive",
      "visual_job_version": 3,
      "request": "把这组证据丰富的开源发布材料做成 launch 系列。使用一个 poster output、四张 cards,artifact roles 依次为 judgment、evidence、capability、case;每张绑定不同当前强证据,不生成额外 overview。只输出 Visual Job JSON。",
      "source_text": "发布判断:Northstar 1.0 把可复核交付作为默认工作方式。当前 benchmark:在官方 40 项回归集中,36 项一次通过。当前能力:每次执行都会保存输入、步骤和哈希回执。当前案例:示例团队用回执重建了前一晚的发布过程。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "source_units": [
        4,
        4
      ],
      "artifact_outputs": [
        4,
        4
      ],
      "required_artifact_roles": [
        "judgment",
        "evidence",
        "capability",
        "case"
      ],
      "required_contract_fields": [
        "cards"
      ],
      "required_card_term_groups": [
        [
          "可复核"
        ],
        [
          "40",
          "36"
        ],
        [
          "输入",
          "哈希回执"
        ],
        [
          "示例团队",
          "重建"
        ]
      ],
      "exclusive_card_term_groups": true,
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "Northstar 1.0",
            "可复核"
          ],
          "contract_terms": [
            "可复核"
          ]
        },
        {
          "source_terms": [
            "40",
            "36"
          ],
          "contract_terms": [
            "40",
            "36"
          ]
        },
        {
          "source_terms": [
            "输入",
            "步骤",
            "哈希回执"
          ],
          "contract_terms": [
            "输入",
            "哈希回执"
          ]
        },
        {
          "source_terms": [
            "示例团队",
            "重建"
          ],
          "contract_terms": [
            "示例团队",
            "重建"
          ]
        }
      ],
      "exclusive_source_contract_mappings": true,
      "required_terms": [
        "Northstar",
        "40",
        "哈希回执",
        "示例团队"
      ]
    },
    {
      "id": "open-source-library-adaptive",
      "visual_job_version": 3,
      "request": "用 documentary register 介绍这个开源 Library/API。使用一个 poster output 和三张 cards,artifact roles 依次为 contract、example、boundary;不要写 launch 金句,不要补兼容性或性能。只输出 Visual Job JSON。",
      "source_text": "公开契约:parse(input) 接收 UTF-8 字符串并返回节点数组。最小示例:const nodes = parse(source)。集成边界:调用方负责读取文件和保存结果,库本身不访问网络。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "source_units": [
        3,
        3
      ],
      "source_unit_assignment": "one-to-one",
      "artifact_outputs": [
        3,
        3
      ],
      "required_artifact_roles": [
        "contract",
        "example",
        "boundary"
      ],
      "required_contract_fields": [
        "cards"
      ],
      "required_card_term_groups": [
        [
          "parse(input)",
          "节点数组"
        ],
        [
          "const nodes",
          "parse(source)"
        ],
        [
          "调用方",
          "不访问网络"
        ]
      ],
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "parse(input)",
            "节点数组"
          ],
          "contract_terms": [
            "parse(input)",
            "节点数组"
          ]
        },
        {
          "source_terms": [
            "const nodes",
            "parse(source)"
          ],
          "contract_terms": [
            "const nodes",
            "parse(source)"
          ]
        },
        {
          "source_terms": [
            "调用方",
            "不访问网络"
          ],
          "contract_terms": [
            "调用方",
            "不访问网络"
          ]
        }
      ],
      "required_terms": [
        "UTF-8",
        "parse(source)",
        "不访问网络"
      ],
      "forbidden_terms": [
        "性能领先",
        "全面兼容",
        "重新定义"
      ]
    },
    {
      "id": "open-source-stale-evidence",
      "visual_job_version": 3,
      "request": "处理这个 UI 工具,只使用当前证据。使用一个 poster output 和两张 cards,artifact roles 依次为 interface、result;旧品牌截图必须标为 stale 或 unusable,不能被 artifact 引用或出现在可见卡片里。只输出 Visual Job JSON。",
      "source_text": "当前产品名:ClearDesk。当前界面:任务页显示输入、运行状态和回执。当前结果:完成后可以下载带 SHA-256 的报告。旧素材:LegacyDesk 2023 仪表盘截图,品牌和界面都已经弃用。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "source_units": [
        3,
        4
      ],
      "artifact_outputs": [
        2,
        2
      ],
      "required_artifact_roles": [
        "interface",
        "result"
      ],
      "required_contract_fields": [
        "cards"
      ],
      "required_card_term_groups": [
        [
          "任务页",
          "运行状态"
        ],
        [
          "SHA-256",
          "报告"
        ]
      ],
      "exclusive_card_term_groups": true,
      "required_source_contract_mappings": [
        {
          "source_terms": [
            "任务页",
            "运行状态"
          ],
          "contract_terms": [
            "任务页",
            "运行状态"
          ]
        },
        {
          "source_terms": [
            "SHA-256",
            "报告"
          ],
          "contract_terms": [
            "SHA-256",
            "报告"
          ]
        }
      ],
      "exclusive_source_contract_mappings": true,
      "rejected_source_expectations": [
        {
          "source_terms": [
            "LegacyDesk",
            "2023"
          ],
          "strength": "unusable",
          "freshness": "stale"
        }
      ],
      "required_terms": [
        "ClearDesk",
        "任务页",
        "SHA-256"
      ],
      "forbidden_terms": [
        "LegacyDesk",
        "2023"
      ]
    },
    {
      "id": "content-preserve-voice",
      "forbidden_titles": [
        "框越少越好"
      ],
      "request": "把下面短文排成一张长阅读卡。只做排版。只输出 Visual Job JSON。",
      "source_text": "我起初觉得框越少越好。后来试了一次,发现没有分组,读起来反而更费劲。现在我会先看内容;如果一条线能让关系清楚,就留着。",
      "publish_target": "long-read",
      "tier": "stable",
      "modes": [
        "long"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "body"
      ],
      "required_terms": [
        "我起初觉得框越少越好。",
        "后来试了一次,发现没有分组,读起来反而更费劲。",
        "现在我会先看内容;如果一条线能让关系清楚,就留着。"
      ]
    },
    {
      "id": "content-summary-conditions",
      "request": "把下面短文提炼成一张长阅读卡。只输出 Visual Job JSON。",
      "source_text": "缓存可以减少重复读取,但仅当数据仍然有效时才能复用。除非已经确认过期,否则不必重新读取。数据过期时必须重新读取。",
      "publish_target": "long-read",
      "tier": "stable",
      "modes": [
        "long"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "body"
      ],
      "required_terms": [
        "有效",
        "除非",
        "过期",
        "重新读取"
      ],
      "required_contract_patterns": [
        "(?:仅(?:当|在)?|只有)[^。!?;\"\\n]{0,40}有效[^。!?;\"\\n]{0,20}复用"
      ]
    },
    {
      "id": "content-peer-groups",
      "request": "把三个同级注意事项排成一张长阅读卡,保留原文。只输出 Visual Job JSON。",
      "source_text": "字号:让文字看得清。间距:让分组看得清。对齐:让顺序看得清。",
      "publish_target": "long-read",
      "tier": "stable",
      "modes": [
        "long"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "body"
      ],
      "required_terms": [
        "字号:让文字看得清。",
        "间距:让分组看得清。",
        "对齐:让顺序看得清。"
      ]
    },
    {
      "id": "content-no-fake-formula",
      "request": "把这个观点整理成一张长阅读卡。只输出 Visual Job JSON。",
      "source_text": "舒服的排版让人愿意继续读。适当留白有帮助,但必要的解释不能因为画面空一些就删掉。",
      "publish_target": "long-read",
      "tier": "stable",
      "modes": [
        "long"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "body"
      ],
      "required_terms": [
        "必要的解释",
        "不能"
      ],
      "forbidden_terms": [
        "=",
        "×",
        "÷",
        "→"
      ]
    },
    {
      "id": "content-supported-formula",
      "request": "为下面关系做一张正文关系图,保留原有公式作为关系标题,并用层级说明组成项。只输出 Visual Job JSON。",
      "source_text": "总时长 = 等待时长 + 执行时长。两段依次发生,互不重叠;如果并行执行,就不能直接相加。",
      "publish_target": "article-body",
      "tier": "stable",
      "modes": [
        "article-diagram"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "formula",
        "sentence",
        "structure"
      ],
      "required_terms": [
        "总时长",
        "等待时长",
        "执行时长",
        "不重叠",
        "并行"
      ]
    },
    {
      "id": "revise-text-heavy",
      "kind": "revision",
      "request": "根据视觉批评减少次要文字并重新建立单一焦点。Visual Job 必须恰好一个 output,poster contract 必须恰好包含一张 cards[0],不得用增加卡片分散文字;artifact 的 visual_plan.visual_metaphor 使用 null。",
      "source_text": "真正重要的不是保存更多,而是让下一次任务能找到需要的那一条。",
      "publish_target": "social-series",
      "tier": "stable",
      "modes": [
        "poster"
      ],
      "outputs": [
        1,
        1
      ],
      "artifact_outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "cards"
      ],
      "required_terms": [
        "下一次",
        "找到"
      ],
      "seed_issue": "too_text_heavy",
      "seed_instruction": "For the initial candidate only, use a short source-grounded title, omit kicker/subtitle, and set cards[0].body to exactly five paragraph elements repeating the complete SOURCE sentence verbatim. Do not add headings, items, or benchmark commentary. This bounded repetition is the seeded excess; the revision must remove it while preserving the source meaning."
    },
    {
      "id": "revise-flat-hierarchy",
      "kind": "revision",
      "request": "根据视觉批评把核心关系提升为主视觉,次要说明降级。修订后的 whiteboard contract 使用一个 chain step,依次交替放置四个 highlight 语义节点“事实、选择、动作、回执”和三个 muted 关系节点“约束、产生、留下”。",
      "source_text": "事实约束选择,选择产生动作,动作留下回执。",
      "publish_target": "whiteboard",
      "tier": "stable",
      "modes": [
        "whiteboard"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "title",
        "steps"
      ],
      "required_terms": [
        "事实",
        "选择",
        "动作",
        "回执"
      ],
      "seed_issue": "flat_hierarchy",
      "seed_instruction": "For the first candidate only, use equal-weight layers or annotation text and do not use the requested highlight/muted chain structure."
    },
    {
      "id": "revise-small-subject",
      "kind": "revision",
      "request": "根据视觉批评放大主体,使缩略图中仍能看清核心对象。修订后光束与目标共同占据至少 60% 画布宽和 70% 画布高,目标纸片至少 420×260,并与来源短句进入同一视觉场,不留下大块无功能中心空白;目标内来源文字使用 36px/1.3,内边距不超过 24px,所有阴影范围不超过 8px。",
      "source_text": "注意力像一束窄光,只照亮当前最重要的信息。",
      "publish_target": "article-body",
      "tier": "studio",
      "modes": [
        "editorial-image"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "use",
        "aspect",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "注意力",
        "窄光"
      ],
      "seed_issue": "subject_too_small",
      "seed_instruction": "For the first candidate only, ignore the final size targets: keep the target at or below 160x100 and the beam below 25% of the canvas. Put no long text inside the small object; use only 重点 or leave it empty, and place the 36px source sentence in a separate safe text area."
    },
    {
      "id": "revise-generic-metaphor",
      "kind": "revision",
      "request": "根据视觉批评换掉通用 AI 大脑隐喻,改成来源特有的可检索把手。修订后的“旧工作”标签必须留在索引卡内部且 top 至少 16px,索引卡主句逐字显示“记忆不是仓库”;把手作为索引卡的同级元素放在相邻位置,不用负值把带文字的子元素推出父框;所有可读文字保持在各自 framed container 内。",
      "source_text": "记忆不是仓库;关键是下一次任务能否用清晰把手找到旧工作。",
      "publish_target": "article-body",
      "tier": "studio",
      "modes": [
        "editorial-image"
      ],
      "outputs": [
        1,
        1
      ],
      "required_contract_fields": [
        "use",
        "aspect",
        "composition_required",
        "content_html",
        "custom_css"
      ],
      "required_terms": [
        "记忆",
        "把手"
      ],
      "forbidden_terms": [
        "AI 大脑",
        "AI brain"
      ],
      "seed_issue": "generic_ai_metaphor",
      "seed_instruction": "For the first candidate, make generic_ai_metaphor the only defect: keep body text at least 36px, use token-derived surface fills only, keep shadows at 8px or less, and keep every framed label mechanically valid. If the handle contains 清晰把手, make it at least 160x130 with a text area at least 130px wide."
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall